SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2402.04467 · ICML · 2024

DySLIM: Dynamics Stable Learning by Invariant Measure for Chaotic Systems

Stephan Hoyer, Fei Sha, Yair Schiff, Volodymyr Kuleshov, Zhong Wan, Jeffrey Parker, Leonardo Zepeda-N Ú Ñez

arXiv · PDF · Open in the Atlas

Code that ran

8 of 9 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 8 failures of our instrument; 1 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2402.04467.json · badge: /api/ran/2402.04467.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
google-research/swirl-dynamics canonical (classifier label)
classifier basis: census
8 ran · 1 no recorded run
FunctionStatusWhere it lives
ConvLayer Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
google-research/swirl-dynamics/swirl_dynamics/lib/layers/convolutions.py
pointer only (licence: NOASSERTION) · get_code("4ddae757fbf45c59")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, google-research/swirl-dynamics (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

default_init Ran
ran; our contract draft was wrong, not the code
google-research/swirl-dynamics/swirl_dynamics/lib/diffusion/unets.py
pointer only (licence: NOASSERTION) · get_code("5aeb858a9d4f09ef")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, google-research/swirl-dynamics (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_fixed_sincos_position_embedding Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
google-research/swirl-dynamics/swirl_dynamics/lib/diffusion/vivit.py
pointer only (licence: NOASSERTION) · get_code("8b0f3ba3d78744f5")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, google-research/swirl-dynamics (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

logsnr2sigma Ran
ran; our contract draft was wrong, not the code
google-research/swirl-dynamics/swirl_dynamics/lib/diffusion/diffusion.py
pointer only (licence: NOASSERTION) · get_code("0dedf57c9f9834aa")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, google-research/swirl-dynamics (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

reshape_2d_to_1d_factorized Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
google-research/swirl-dynamics/swirl_dynamics/lib/diffusion/reshape_utils.py
pointer only (licence: NOASSERTION) · get_code("e807b0b621b7ab69")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, google-research/swirl-dynamics (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

reshape_3d_to_1d_factorized Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
google-research/swirl-dynamics/swirl_dynamics/lib/diffusion/reshape_utils.py
pointer only (licence: NOASSERTION) · get_code("6cf5d97549e344fd")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, google-research/swirl-dynamics (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

reshape_to_2d_factorized Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
google-research/swirl-dynamics/swirl_dynamics/lib/diffusion/reshape_utils.py
pointer only (licence: NOASSERTION) · get_code("05b7120cabeae3d3")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, google-research/swirl-dynamics (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

sigma2logsnr Ran
ran; our contract draft was wrong, not the code
google-research/swirl-dynamics/swirl_dynamics/lib/diffusion/diffusion.py
pointer only (licence: NOASSERTION) · get_code("d2baaeb01b155412")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, google-research/swirl-dynamics (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

position_embedding Not yet run
unverified (harvested, no recorded run)
google-research/swirl-dynamics/swirl_dynamics/lib/diffusion/unets.py
pointer only (licence: NOASSERTION) · get_code("e586d3a42e63085d")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, google-research/swirl-dynamics (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 9 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Learning dynamics from dissipative chaotic systems is notoriously difficult due to their inherent instability, as formalized by their positive Lyapunov exponents, which exponentially amplify errors in the learned dynamics. However, many of these systems exhibit ergodicity and an attractor: a compact and highly complex manifold, to which trajectories converge in finite-time, that supports an invariant measure, i.e., a probability distribution that is invariant under the action of the dynamics, which dictates the long-term statistical behavior of the system. In this work, we leverage this structure to propose a new framework that targets learning the invariant measure as well as the dynamics, in contrast with typical methods that only target the misfit between trajectories, which often leads to divergence as the trajectories' length increases. We use our framework to propose a tractable and sample efficient objective that can be used with any existing learning objectives. Our Dynamics Stable Learning by Invariant Measure (DySLIM) objective enables model training that achieves better point-wise tracking and long-term statistical accuracy relative to other learning objectives. By targeting the distribution with a scalable regularization term, we hope that this approach can be extended to more complex systems exhibiting slowly-variant distributions, such as weather and climate models. Code to reproduce our experiments is available here.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2402.04467")
get_code_for_paper("2402.04467")
have("2402.04467")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2402.04467.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2402.04467.svg)](https://syntology.ai/paper/2402.04467)

Connect an agent — have() is free.